An efficient Naive Bayes approach to category-level object detection

We present a fast Bayesian algorithm for category-level object detection in natural images. We modify the popular Naive Bayes Nearest Neighbour classification algorithm to make it suitable for evaluating multiple sub-regions in an image, and offer a fast, filtering-based alternative to the multi-sca...

Full description

Saved in:
Bibliographic Details
Main Authors: Terzic, Kasim, du Buf, J. M. H.
Format: Conference Proceeding
Language:English
Subjects:
Complexity theory
Computer vision
Kernel
Nearest neighbour
Object detection
Real time systems
Robot vision
Robots
Testing
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a fast Bayesian algorithm for category-level object detection in natural images. We modify the popular Naive Bayes Nearest Neighbour classification algorithm to make it suitable for evaluating multiple sub-regions in an image, and offer a fast, filtering-based alternative to the multi-scale sliding window approach. Our algorithm is example-based and requires no learning. Tests on standard datasets and robotic scenarios show competitive detection rates and real-time performance of our algorithm.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2014.7025332